Method and apparatus for session interaction, and device and storage medium

By selecting and presenting the selection controls and mentioning information of the target digital assistant in the conversation, the problem of insufficient flexibility in interaction between users and digital assistants is solved, and the convenience and efficiency of selecting non-session member assistants to reply messages is achieved.

WO2025156590A1PCT designated stage Publication Date: 2025-07-31BEIJING ZITIAO NETWORK TECH CO LTD
View PDF 5 Cites 0 Cited by

Patent Information

Application Number
PCT/CN2024/108904
Authority / Receiving Office
WO · WO
Patent Type
Applications
Current Assignee / Owner
Filing Date
2024-07-31
Publication Date
2025-07-31

AI Technical Summary

Technical Problem

In the prior art, the user has insufficient flexibility in interacting with the digital assistant, and it is impossible to select a digital assistant that does not belong to a session member to reply in the conversation.

Method used

Provided is a method and apparatus that allows a user to select one or more target digital assistants in a target session, present user messages and reply to by these assistants, including presenting selection controls and mention information in an interface, supporting the addition of new assistants, and recommending matching assistants when typing.

Benefits of technology

It improves the user's interaction convenience with digital assistants, allows non-session member assistants to reply messages, and enhances the flexibility and efficiency of interaction.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN2024108904_31072025_PF_FP_ABST
    Figure CN2024108904_31072025_PF_FP_ABST
Patent Text Reader

Abstract

Provided in the embodiments of the present disclosure are a method and apparatus for session interaction, and a device and a storage medium. The method comprises: receiving a choice made by a user regarding one or more target digital assistants in a target session, wherein the one or more target digital assistants are not members of the target session, and members of the target session comprise a plurality of digital assistants; displaying a first message sent by the user in the target session; and displaying one or more reply messages, which are respectively sent by the one or more target digital assistants for the first message. Thus, a user can select a digital assistant which does not belong to a session to reply to a message sent by the user, thereby improving the convenience of interaction between the user and the digital assistant.
Need to check novelty before this filing date? Find Prior Art

Description

Method, apparatus, device, and storage medium for conversation interaction Technical Field

[0001] Example embodiments of the present disclosure generally relate to the field of computers, and more particularly, to methods, devices, apparatuses, and computer-readable storage media for conversational interaction. Background Art

[0002] With the development of information technology, various terminal devices can provide a variety of services for people in work and daily life. Applications that provide these services can be deployed on these devices. These devices or applications can provide users with digital assistant-like functions to assist them in using the device or application. Improving the flexibility of user interaction with digital assistants is a current technical challenge.

[0003] Summary of the Invention

[0004] In a first aspect of the present disclosure, a method for conversation interaction is provided. The method includes: receiving a user's selection of one or more target digital assistants in a target conversation, the one or more target digital assistants not being members of the target conversation, and the members of the target conversation including multiple digital assistants; presenting a first message sent by the user in the target conversation; and presenting one or more reply messages to the first message, respectively sent by the one or more target digital assistants.

[0005] In a second aspect of the present disclosure, a device for conversation interaction is provided. The device includes: a selection receiving module configured to receive a user's selection of one or more target digital assistants in a target conversation, the one or more target digital assistants not being members of the target conversation, and the members of the target conversation including multiple digital assistants; a message presenting module configured to present a first message sent by the user in the target conversation; and a reply message presenting module configured to present one or more reply messages to the first message, respectively sent by the one or more target digital assistants.

[0006] In a third aspect of the present disclosure, an electronic device is provided. The device includes at least one processing unit; and at least one memory coupled to the at least one processing unit and storing instructions for execution by the at least one processing unit. When executed by the at least one processing unit, the instructions cause the device to perform the method of the first aspect.

[0007] In a fourth aspect of the present disclosure, a computer-readable storage medium is provided, wherein a computer program is stored on the computer-readable storage medium, and the computer program can be executed by a processor to implement the method of the first aspect.

[0008] It should be understood that the content described in this summary section is not intended to limit the key features or important features of the embodiments of the present disclosure, nor is it intended to limit the scope of the present disclosure. Other features of the present disclosure will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] The above and other features, advantages and aspects of the embodiments of the present disclosure will become more apparent with reference to the following detailed description in conjunction with the accompanying drawings. In the accompanying drawings, the same or similar reference numerals represent the same or similar elements, wherein:

[0010] FIG1 shows a schematic diagram of an example environment in which embodiments of the present disclosure can be implemented;

[0011] 2A to 2F are schematic diagrams illustrating example interfaces for conversation interaction according to some embodiments of the present disclosure;

[0012] 3A to 3E are schematic diagrams illustrating example interfaces for conversation interaction according to other embodiments of the present disclosure;

[0013] 4A to 4C are schematic diagrams showing example interfaces for conversation interaction according to further embodiments of the present disclosure;

[0014] 5A to 5C illustrate schematic diagrams of example interfaces for adding a digital assistant according to some embodiments of the present disclosure;

[0015] 6A to 6F are schematic diagrams illustrating example interfaces for conversation interaction according to some embodiments of the present disclosure;

[0016] FIG7 shows a flowchart of a process of conversation interaction according to some embodiments of the present disclosure;

[0017] FIG8 shows a block diagram of an apparatus for conversation interaction according to some embodiments of the present disclosure; and

[0018] FIG9 illustrates a block diagram of a device capable of implementing various embodiments of the present disclosure. DETAILED DESCRIPTION

[0019] It is understandable that before using the technical solutions disclosed in the various embodiments of this disclosure, the type, scope of use, usage scenarios, etc. of the personal information involved in this disclosure should be informed to the user and the user's authorization should be obtained in an appropriate manner in accordance with relevant laws and regulations.

[0020] For example, in response to a user's active request, a prompt message is sent to the user to clearly inform the user that the operation requested will require the acquisition and use of the user's personal information. This allows the user to independently choose whether to provide personal information to the electronic device, application, server, storage medium, or other software or hardware that performs the operations of the disclosed technical solution based on the prompt message.

[0021] As an optional but non-limiting implementation, in response to receiving a user's active request, the prompt information may be sent to the user in the form of a pop-up window, in which the prompt information may be presented in text form. Furthermore, the pop-up window may also contain a selection control for the user to select "agree" or "disagree" to provide personal information to the electronic device.

[0022] It is understandable that the above notification and user authorization process are merely illustrative and do not limit the implementation of the present disclosure. Other methods that comply with relevant laws and regulations may also be applied to the implementation of the present disclosure.

[0023] It is understandable that the data involved in this technical solution (including but not limited to the data itself, the acquisition or use of the data) must comply with the requirements of relevant laws, regulations and relevant provisions.

[0024] The following describes embodiments of the present disclosure in more detail with reference to the accompanying drawings. Although certain embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be construed as limited to the embodiments described herein. Rather, these embodiments are provided to provide a more thorough and complete understanding of the present disclosure. It should be understood that the drawings and embodiments of the present disclosure are for illustrative purposes only and are not intended to limit the scope of protection of the present disclosure.

[0025] It should be noted that the titles of any section / subsection provided herein are not limiting. Various embodiments are described throughout this document, and any type of embodiment may be included under any section / subsection. Furthermore, the embodiments described in any section / subsection may be combined in any manner with any other embodiments described in the same section / subsection and / or in different sections / subsections.

[0026] Herein, unless explicitly stated otherwise, executing a step “in response to A” does not mean executing the step immediately after “A” but may include one or more intermediate steps.

[0027] In the description of the embodiments of the present disclosure, the term "including" and similar terms should be understood as open inclusion, that is, "including but not limited to". The term "based on" should be understood as "based at least in part on". The term "one embodiment" or "the embodiment" should be understood as "at least one embodiment". The term "some embodiments" should be understood as "at least some embodiments". Other explicit and implicit definitions may be included below. The terms "first", "second", etc. may refer to different or the same objects. Other explicit and implicit definitions may be included below.

[0028] As briefly mentioned above, people are collaborating more and more with language model robots, and people are expanding the boundaries of their capabilities by means of dialogue with digital assistants. Currently, users can interact with digital assistants in a conversation between the user and a single digital assistant (for example, a one-on-one chat). Users can also interact with digital assistants in a conversation between the user and multiple digital assistants (for example, a group chat). However, all of the above methods require that the digital assistant is a member of the conversation. Accordingly, in the conversation between the user and the digital assistant, the system determines the matching digital assistant based on the user's intention to reply to the user's message.

[0029] In view of this, embodiments of the present disclosure propose an improved solution for conversational interaction. According to various embodiments of the present disclosure, a user's selection of one or more target digital assistants in a target conversation is received, and the one or more target digital assistants are not members of the target conversation; a first message sent by the user in the target conversation is presented; and one or more reply messages to the first message, respectively sent by the one or more target digital assistants, are presented. Thus, the user can select a digital assistant that is not part of the conversation to reply to the message it sent, thereby improving the convenience of the user's interaction with the digital assistant.

[0030] Sample Environment

[0031] 1 shows a schematic diagram of an example environment 100 in which embodiments of the present disclosure can be implemented. In the example environment 100, an application 120 is installed in a terminal device 110. A user 140 can interact with the application 120 via the terminal device 110 and / or a device attached to the terminal device 110.

[0032] In some embodiments, application 120 can be any suitable application that can provide query services. In environment 100 of FIG1 , if application 120 is active, terminal device 110 can present page 150 of application 120. Page 150 can include various pages provided by application 120, such as session interaction pages, query pages, search pages, search result presentation pages, and so on.

[0033] In some embodiments, the terminal device 110 communicates with the server 130 to enable the supply of services to the application 120. The terminal device 110 can be any type of mobile terminal, fixed terminal or portable terminal, including a mobile phone, a desktop computer, a laptop computer, a notebook computer, a netbook computer, a tablet computer, a media computer, a multimedia tablet, a personal communication system (PCS) device, a personal navigation device, a personal digital assistant (PDA), an audio / video player, a digital camera / camcorder, a positioning device, a television receiver, a radio broadcast receiver, an e-book device, a gaming device or any combination thereof, including accessories and peripherals of these devices or any combination thereof. In some embodiments, the terminal device 110 can also support any type of interface for the user (such as a "wearable" circuit, etc.). The server 130 can be various types of computing systems / servers that can provide computing power, including but not limited to mainframes, edge computing nodes, computing devices in cloud environments, and the like.

[0034] It should be understood that the structure and function of the various elements in the environment 100 are described for illustrative purposes only and do not imply any limitation on the scope of the present disclosure.

[0035] Some example embodiments of the present disclosure will continue to be described with reference to the accompanying drawings. It should be understood that the pages shown in the accompanying drawings are merely examples, and various page designs may actually exist. The various graphic elements in the page may have different arrangements and different visual representations, one or more of which may be omitted or replaced, and one or more other elements may also exist. The embodiments of the present disclosure are not limited in this respect. In addition, the example embodiments will be described primarily with respect to the terminal device 110 hereinafter. It should be understood that the actions described with respect to the terminal device 110 may be performed by the application 120 on the terminal device 110, or may be performed by the application 120 in collaboration with its service end (e.g., server 130).

[0036] The following describes the process for conversation interaction disclosed herein with reference to three examples, Figures 2A to 2F, Figures 3A to 3E, and Figures 4A to 4C. Figures 2A to 2F illustrate schematic diagrams of example interfaces 200A to 200F for conversation interaction according to some embodiments of the present disclosure. Figures 3A to 3E illustrate schematic diagrams of example interfaces 300A to 300E for conversation interaction according to other embodiments of the present disclosure. Figures 4A to 4C illustrate schematic diagrams of example interfaces 400A to 400C for conversation interaction according to yet other embodiments of the present disclosure.

[0037] In some embodiments, terminal device 110 receives a user's selection of one or more target digital assistants in a target session. In some embodiments, one or more digital assistants are not members of the target session, and the target session includes multiple digital assistants. In some examples, user 140 can select one or more digital assistants that are not members of the target session in the target session (e.g., a session between user 140 and a preset digital assistant) to reply to a message sent by user 140.

[0038] In some embodiments, the terminal device 110 may receive a user's selection of one or more digital assistants in a target session in the following manner: The terminal device 110 presents a selection control for at least one digital assistant in the interface of the target session. The terminal device 110 then receives a trigger operation for a corresponding selection control for one or more target digital assistants in the at least one digital assistant.

[0039] As shown in the example interface 200A of FIG2A , the terminal device 110 presents a selection control 212 for assistant A, a selection control 213 for assistant B, a selection control 214 for assistant C, a selection control 215 for assistant D, and so on in the interface of the target session. In some examples, the terminal device 110 may also present a selection control 212 for assistant A, a selection control 213 for assistant B, a selection control 214 for assistant C, and so on in the operation bar 211 included in the interface of the target session. For the selection controls 212 for assistant A, 213 for assistant B, 214 for assistant C, 215 for assistant D, and so on presented by the terminal device 110, the user 140 may click on the aforementioned selection controls to select one or more target digital assistants.

[0040] In some embodiments, if the terminal device 110 receives a triggering operation for the selection controls corresponding to one or more target digital assistants, the corresponding selection controls of the one or more target digital assistants can be presented in a predetermined style. In some examples, when the terminal device 110 supports the user 140 to select one or more digital assistants, if the user 140 clicks the selection control of assistant A and the selection control of digital assistant B, assistant A and assistant B are in the selected state, and the send button is activated. As shown in the example interfaces 200A to 200B of Figures 2A to 2B, if the terminal device 110 receives the user 140 clicking the selection control 212 of assistant A and the selection control 213 of assistant B, the selection control 212 of assistant A and the selection control 213 of assistant B are highlighted. For example, the selection control 212 and the selection control 213 are filled with different colors or patterns.

[0041] In other examples, when the terminal device 110 supports the user 140 to select a digital assistant, if the user 140 clicks the selection control of Assistant A, Assistant A is in the selected state, and the send button of the input box 321 is activated. As shown in the example interfaces 300A to 300B of Figures 3A to 3B, if the terminal device 110 receives that the user 140 clicks the selection control 312 of Assistant A, the selection control 312 of Assistant A can be presented in the input box 321.

[0042] In some embodiments, user 140 can cancel the selected target digital assistant at any time. The canceled target digital assistant will no longer reply to user 140's messages. As shown in example interfaces 200B to 200C in Figures 2B to 2C, if user 140 clicks the close control 221 for assistant B, assistant B is deselected. As shown in example interface 300B in Figure 3B, if user 140 clicks the close control 322 for assistant A, assistant A is deselected.

[0043] In some embodiments, when user 140 selects one or more target digital assistants, if the user clicks the input box, the terminal device 110 only presents the identification information of the one or more target digital assistants in the area above the input box. As shown in example interface 200D in Figure 2D, when user 140 selects Assistant A and Assistant B, if the user 140 clicks input box 241, the terminal device 110 presents the identification information of Assistant A and Assistant B in area 245 above input box 241.

[0044] In some embodiments, after user 140 selects one or more target digital assistants, terminal device 110 may display a prompt in the input box included in the interface of the target conversation. For example, if user 140 selects a digital assistant, terminal device 110 may display a prompt such as "Say to XX Assistant..." If user 140 selects two digital assistants, terminal device 110 may display a prompt such as "Say to XX Assistant and XXX Assistant..." If user 140 selects multiple digital assistants, terminal device 110 may display a prompt such as "Say to XX Assistant, XXX Assistant, etc..." If user 140 selects a digital assistant with a long name, terminal device 110 may display a prompt such as "Say to XX Assistant, XXX..." As shown in Figure 2B, if user 140 selects Assistant A and Assistant B, terminal device 110 displays "Send to Assistant A and Assistant B..." in input box 223. As shown in Figure 3B, if user 140 selects Assistant A, terminal device 110 displays "Send to Assistant A" or "Say to Assistant A" in input box 321.

[0045] In some embodiments, the terminal device 110 presents the first message sent by the user in the target session. In some embodiments, the terminal device 110 may present the first message sent by the user in the target session in the following manner. The terminal device 110 receives user input for one or more target digital assistants. Subsequently, in response to a send operation input by the user, the terminal device 110 presents the user input and a mention of the one or more target digital assistants as the first message.

[0046] In some examples, after selecting one or more target digital assistants, user 140 can enter a message in the input box. Then, if the terminal device 110 receives the message from user 140 clicking the send button to send the message entered, the terminal device 110 presents the mention information for one or more digital assistants (for example, @XX assistant) and the message entered by the user in the input box in the interface of the target session. In some embodiments, the mention information of one or more digital assistants presented by the terminal device 110 in the interface of the target session may be: the mention information automatically generated by the terminal device 110 after receiving the message from user 140 clicking the send button. In some embodiments, the terminal device 110 may display the mention information at the forefront of the first message.

[0047] As shown in example interfaces 200D to 200E in Figures 2D to 2E , after selecting Assistant A and Assistant B, user 140 can enter a message 242 in the input box. Then, upon receiving an indication from user 140 that they have clicked on Send button 221 to send their input message 242, terminal device 110 presents message 251 in the target conversation interface. Message 251 includes a mention 254 "@Assistant A @Assistant B" automatically generated by terminal device 110 and the message 242 entered by user 140.

[0048] As shown in example interfaces 300C to 300D in Figures 3C to 3D , after selecting Assistant A, user 140 can enter a message 332 in input box 321. Then, upon receiving a click of the Send button by user 140 to send message 332, terminal device 110 presents message 341 in the target conversation interface. Message 341 includes a mention 343 "@Assistant A" automatically generated by terminal device 110 and message 322 entered by user 140.

[0049] In some embodiments, the mention information is presented in the first message in a preset style, and the preset style is associated with the number of one or more target digital assistants. The terminal device 110 can present the mention information for one or more target digital assistants in a preset style. In some examples, the terminal device 110 can present the mention information in an eye-catching style, such as bold text and bold ordinary text. In some examples, if the user 140 selects a digital assistant, the terminal device 110 can present the mention information about the digital assistant at the forefront of the first message. If the user 140 selects multiple digital assistants, the terminal device 110 can present multiple mention information about multiple digital assistants at the forefront of the first message.

[0050] In some embodiments, the terminal device 110 may also present the first message sent by the user in the target conversation in another manner as follows: If the terminal device 110 receives a user selection of one or more target digital assistants from at least one digital assistant, the terminal device 110 presents the first message mentioning the one or more target digital assistants, respectively.

[0051] In some examples, after user 140 selects one or more target digital assistants, terminal device 110 automatically sends a message mentioning one or more target digital assistants. If one target digital assistant is selected, a single mention message is sent. If multiple target digital assistants are selected, multiple mention messages are sent. As shown in example interfaces 400A to 400C in Figures 4A to 4C, after user 140 selects Assistant A by clicking on the selection control 412 for Assistant A from the selection controls corresponding to at least one assistant, terminal device 110 presents message 421 in the interface of the target session. Message 421 includes a mention of Assistant A, "@A Assistant." After user 140 selects Assistant A and Assistant B by clicking on the selection control 412 for Assistant A and the selection control 413 for Assistant B from the selection controls corresponding to at least one assistant, terminal device 110 presents messages 431 and 433 in the interface of the target session. Message 431 includes a mention of Assistant A, "@A Assistant," and message 433 includes a mention of Assistant B, "@B Assistant." In this way, responses from the digital assistants can be quickly obtained.

[0052] In some embodiments, user 140 clicks the close control of the target digital assistant to cancel the selected state of the target digital assistant, but the sent message is not withdrawn. Clicking the same target digital assistant again will not send it repeatedly until the interface of the current session is exited. After exiting and re-entering, the sending is triggered again. In the example interface 400C shown in Figure 4C, if user 140 clicks the close control 435 of assistant B to cancel the selected state of assistant B, the sent message 433 is not withdrawn. Select assistant B again and the message 433 is not sent repeatedly until the interface of the current session is exited.

[0053] In some embodiments, the terminal device 110 presents one or more reply messages for the first message, respectively issued by one or more digital assistants. In some examples, the terminal device 110 presents one or more reply messages for the first message issued in the target conversation, respectively issued by one or more target digital assistants. As shown in the example interface 200E in Figure 2E, for the message 251 "@A assistant @B assistant what kind of person are you", the terminal device 110 presents a reply message 252 issued by assistant A and a reply message 253 issued by assistant B. As shown in the example interface 300D in Figure 3D, for the message 341 "@A assistant what kind of person are you", the terminal device 110 presents a reply message 342 issued by assistant A.

[0054] In some embodiments, the terminal device 110 presents one or more first reply messages to a first message mentioning one or more target digital assistants, including corresponding introduction information for the one or more target digital assistants. It is understandable that, in the case where the first message only includes mention information for one or more target digital assistants, the reply message to the first message includes introduction information for the one or more target digital assistants.

[0055] As shown in the example interface 400B in FIG4B , when the user 140 selects assistant A, the terminal device 110 presents a reply message 422 issued by assistant A to introduce assistant A in response to the message 421 “@assistant A”. As shown in the example interface 400C in FIG4C , when the user 140 selects assistant A and assistant B, the terminal device 110 presents a reply message 432 issued by assistant A to introduce assistant A in response to the message 431 “@assistant A”. Then, in response to the message 433 “@assistant B”, the terminal device 110 presents a reply message 434 issued by assistant B to introduce assistant B.

[0056] 5A to 5C will continue to describe receiving a user's selection of one or more digital assistants based on triggering an add entry. FIG5A to FIG5C illustrate schematic diagrams of example interfaces 500A to 500C for adding a digital assistant according to some embodiments of the present disclosure.

[0057] In some embodiments, the terminal device 110 presents an add entry for adding a digital assistant in the interface of the target session. In some embodiments, the add entry (sometimes also referred to as a "summoning entry") is used to pull the digital assistant used to reply to the message into the target session. It is understandable that the currently added digital assistant is not a member of the target session. In the example interface 500A shown in Figure 5A, the terminal device 110 can present an add entry 512 in the interface of the target session.

[0058] In some embodiments, if the terminal device 110 detects a trigger operation for adding an entry, it presents assistant information related to at least one candidate digital assistant. As shown in the example interface 500B of Figure 5B, if the user 140 clicks the add entry 512, the terminal device 110 presents a floating layer 521 including assistant information related to at least one candidate digital assistant. In some embodiments, the floating layer 521 also includes a search box 522, and the user 140 can search for the digital assistant they need based on the search box 522.

[0059] In some embodiments, the terminal device 110 may determine these candidate digital assistants based on one or more interaction messages in the target session and / or the digital assistant selected by the user in the target session. In some examples, the terminal device 110 may recommend candidate digital assistants to the user 140 based on the content of the interaction between the user 140 and the digital assistant in the target session. For example, the configuration information of the recommended candidate digital assistant matches the theme of the interaction content. Alternatively or additionally, if the user has previously selected a digital assistant to temporarily participate in the session, a digital assistant may be further recommended based on the user's previous selection.

[0060] In some embodiments, upon receiving a digital assistant addition operation for a target session, the terminal device 110 may present an interaction window of the target session in the first interface area. The terminal device 110 may also present assistant information of multiple candidate digital assistants in another interface area that is at least partially different from the first interface area. In some examples, if a digital assistant addition indication is detected (for example, a control for adding a digital assistant is triggered), the terminal device 110 may display the interaction window of the target session and an assistant recommendation page (which may include assistant information of multiple candidate digital assistants) in split screen. For example, depending on the screen size and / or orientation of the terminal device 110, the interaction window and the assistant recommendation page may be presented in the upper and lower halves of the user interface, respectively, or may be presented in the left and right halves of the user interface, respectively.

[0061] In some embodiments, the terminal device 110 may also present a search entry in the second interface area for searching for a digital assistant from a plurality of candidate digital assistants. That is, a search entry for a digital assistant may be included in the assistant recommendation page. Thus, the user 140 may search for a digital assistant to add to the target session through the search entry.

[0062] In some embodiments, the assistant information of multiple candidate digital assistants is presented in the second interface area according to the grouping of the multiple candidate digital assistants. The terminal device 110 can also group multiple candidate digital assistants, and then present the assistant information corresponding to each group of digital assistants after grouping in the second interface area. As an example, the grouping criteria may include whether the configuration information of the digital assistants is similar, such as the digital assistants in the same group have similar functions. As another example, the grouping criteria may include whether the functions of the digital assistants are associated with the same topic, such as the digital assistants in the same group are all related to travel. Thus, the terminal device 110 clusters and displays multiple candidate digital assistants.

[0063] Then, the terminal device 110 receives a selection of a candidate digital assistant from at least one candidate digital assistant to determine the selected candidate digital assistant as at least a part of one or more target digital assistants. The user 140 selects one or more candidate digital assistants from at least one candidate digital assistant to pull the selected one or more candidate digital assistants into the target session. As shown in example interfaces 500B to 500C in Figures 5B to 5C, the user 140 can select Assistant E from Assistant A, Assistant B, Assistant C, Assistant D, Assistant E, and so on to pull Assistant E into the target session for replying to the first message.

[0064] In some embodiments, the identification information of the selected candidate digital assistant is presented in the preset interface area of ​​the target session to indicate that the selected candidate digital assistant joins the target session. In some examples, if the identification information of the candidate digital assistant selected by the user 140 from at least one candidate digital assistant has been presented in the preset interface area (sometimes also referred to as the "action bar"), the terminal device 110 sets the candidate digital assistant to be in a selected state. If the identification information of the candidate digital assistant selected by the user 140 from at least one candidate digital assistant is not presented in the preset interface area, the terminal device 110 presents the identification information of the candidate digital assistant in the preset interface area.

[0065] In other embodiments, if the identification information of the digital assistants included in the preset interface area reaches a preset capacity, the terminal device 110 removes the identification information of at least one digital assistant that has been presented from the preset interface area. Then, the terminal device 110 adds the identification information of the selected candidate digital assistant to the preset interface area.

[0066] In some examples, if the identification information of the candidate digital assistant selected by the user 140 from at least one candidate digital assistant is not presented in the preset interface area, and the capacity of the preset interface area is full, the terminal device 110 removes the identification information of the at least one digital assistant that has been presented from the preset interface area. Subsequently, the terminal device 110 presents the identification information of the candidate digital assistant in the preset interface area. As shown in the example interfaces 500A to 500C in Figures 5A to 5C, when the preset capacity of the operation bar 511 includes the identification information of the summoning entrance, the identification information of assistant A, the identification information of assistant B, the identification information of assistant C, and the identification information of assistant D, if the user 140 selects assistant E from at least one candidate digital assistant, the terminal device 110 will remove the identification information of assistant D, and then add the identification information 531 of assistant E to the operation bar 511.

[0067] In some embodiments, the currently added digital assistant may be presented at the top of the operation bar and in a selected state. In some examples, if the selected state of the currently added digital assistant is canceled, the identification information of the currently added digital assistant is still presented in the operation bar.

[0068] 6A to 6F will continue to describe receiving a user's selection of one or more target digital assistants in a target conversation when the user enters a mention (e.g., "@"). Figures 6A to 6F illustrate schematic diagrams of example interfaces 600A to 600F for conversational interaction according to some embodiments of the present disclosure.

[0069] In some embodiments, the target session includes an input box. As shown in the example interface 600A in Figure 6A, the target session includes an input box 611. If the terminal device 110 detects user input in the input box, it presents at least one matching digital assistant that matches the user input, and the user input includes mention information. In some examples, in scenarios where the user has selected and / or not selected one or more target digital assistants, if the terminal device 110 detects user input mention information in the input box, it presents at least one matching digital assistant that matches the user input.

[0070] As shown in example interfaces 600A to 600E in Figures 6A to 6E, if terminal device 110 detects that user 140 has clicked input box 611, a keyboard pops up for user 140 to enter a message. After entering message 622, if user 140 continues to enter @, terminal device 110 presents a selection box 632 in the interface of the target conversation. Selection box 632 presented by terminal device 110 includes identification information of the target digital assistant for recommendation.

[0071] Subsequently, if the terminal device 110 detects that the user 140 continues to input @zh, the terminal device 110 presents a selection box 632 in a loading state. Based on the user 140 input @zh 641, the terminal device 110 presents in the selection box 632 the identification information of Zhang Assistant, the identification information of Zi Assistant, Zhou XX, Zhan XX, etc., which are used to recommend matching the user input.

[0072] In some embodiments, the terminal device 110 receives a selection of a matching digital assistant from at least one matching digital assistant, and determines the selected matching digital assistant as at least a part of one or more target digital assistants. As shown in example interfaces 600E to 600F in Figures 6E to 6F, the user 140 can select "Zhang Assistant" from the identification information of Zhang Assistant, the identification information of Zi Assistant, Zhou XX, Zhan XX, etc. recommended by the terminal device 110. Based on the selection of the user 140, the terminal device 110 determines "Zhang Assistant" as a part of one or more target digital assistants.

[0073] Accordingly, when user 140 clicks the selection control 652 of the target digital assistant, the message "@XXX" entered by user 140 disappears. As shown in example interface 600F of FIG6F , when user 140 clicks the selection control 652 of assistant Zhang, the message 641 "@zh" entered by user 140 disappears and becomes message 661.

[0074] In some embodiments, when the terminal device 110 supports the user 140 to select a digital assistant, the terminal device 110, after receiving the target digital assistant selected by the user 140, replaces the selected target digital assistant with the selected target digital assistant. When the terminal device 110 supports the user 140 to select one or more digital assistants, the terminal device 110, after receiving the target digital assistant selected by the user 140, determines the selected target digital assistant as part of the one or more target digital assistants.

[0075] In some embodiments, the terminal device 110 receives a second message sent by the user in the target conversation. If one or more target digital assistants are in a selected state, the terminal device 110 presents one or more reply messages to the second message respectively issued by the one or more target digital assistants. It is understandable that if the user 140 does not cancel the selected state of one or more target digital assistants and continues to send the second message, the terminal device 110 presents one or more reply messages to the second message respectively issued by the one or more target digital assistants.

[0076] In some embodiments, if the terminal device 110 detects that the user has canceled the selection of one or more target digital assistants, it receives a third message sent by the user in the target session. Accordingly, the terminal device 110 presents one or more reply messages to the third message issued by the preset digital assistant in the target session. It is understandable that after the user 140 cancels the selected state of one or more target digital assistants and continues to send the third message, the terminal device 110 presents one or more reply messages to the third message issued by the preset digital assistant. In some embodiments, the preset digital assistant is a member of the target session.

[0077] As shown in example interfaces 200E to 200F in Figures 2E to 2F, after the user 140 cancels the selected state of assistant A and assistant B, he continues to enter a message in the input box 261, and when the message is sent, the terminal device 110 presents a reply message for the message issued by the preset digital assistant. In some embodiments, the preset digital assistant is a member of the target session. As shown in example interfaces 300D to 300E in Figures 3D to 3E, after the user 140 cancels the selected state of assistant A, he continues to enter a message in the input box 316, and when the message is sent, the terminal device 110 presents a reply message for the message issued by the preset digital assistant. In some embodiments, the preset digital assistant is a member of the target session.

[0078] In summary, users can choose a digital assistant that is not part of the conversation to reply to the message it sends, thereby improving the convenience of the user's interaction with the digital assistant.

[0079] Example Process

[0080] FIG7 shows a flow chart of a process 700 for session interaction according to some embodiments of the present disclosure. The process 700 may be implemented at the terminal device 110. The process 700 is described below with reference to FIG1.

[0081] In box 710, the terminal device 110 receives a user's selection of one or more target digital assistants in a target session, the one or more target digital assistants are not members of the target session, and the members of the target session include multiple digital assistants.

[0082] In block 720 , the terminal device 110 presents the first message sent by the user in the target conversation.

[0083] In box 730, the terminal device 110 presents one or more reply messages to the first message respectively issued by one or more target digital assistants.

[0084] In some embodiments, process 700 also includes: in response to receiving a digital assistant add operation for the target session, presenting an interaction window of the target session in a first interface area; and presenting assistant information of multiple candidate digital assistants in a second interface area, the second interface area being at least partially different from the first interface area.

[0085] In some embodiments, the second interface area includes a search portal for searching for a digital assistant from a plurality of candidate digital assistants.

[0086] In some embodiments, assistant information of multiple candidate digital assistants is presented in the second interface area according to the grouping of the multiple candidate digital assistants.

[0087] In some embodiments, process 700 also includes: determining multiple candidate digital assistants based on at least one of: one or more interaction messages in the target session, or a digital assistant selected by the user in the target session; and presenting assistant information of multiple candidate digital assistants for selecting one or more target digital assistants.

[0088] In some embodiments, receiving a user's selection of one or more target digital assistants in a target session includes: presenting a selection control for at least one digital assistant in an interface of the target session; and receiving a trigger operation for the corresponding selection control of one or more target digital assistants in the at least one digital assistant.

[0089] In some embodiments, process 700 also includes: in response to a triggering operation, presenting corresponding selection controls of one or more target digital assistants in a predetermined style.

[0090] In some embodiments, presenting a first message sent by a user in a target conversation includes: receiving user input for one or more target digital assistants; and in response to a send operation for the user input, presenting the user input and mention information for the one or more target digital assistants as the first message.

[0091] In some embodiments, the mention information is presented in the first message in a preset style, and the preset style is associated with the number of the one or more target digital assistants.

[0092] In some embodiments, presenting a first message sent by a user in a target conversation includes: in response to a selection of one or more target digital assistants from at least one digital assistant, presenting a first message that respectively mentions the one or more target digital assistants, and one or more first reply messages respectively include corresponding introductory information for the one or more target digital assistants.

[0093] In some embodiments, receiving a user's selection of one or more target digital assistants in a target session includes: presenting an add entry for adding a digital assistant in an interface of the target session; presenting assistant information related to at least one candidate digital assistant in response to a triggering operation on the add entry; and receiving a selection of a candidate digital assistant from at least one candidate digital assistant to determine the selected candidate digital assistant as at least a part of one or more target digital assistants.

[0094] In some embodiments, identification information of the selected candidate digital assistant is presented in a preset interface area of ​​the target session to indicate that the selected candidate digital assistant joins the target session.

[0095] In some embodiments, process 700 also includes: in response to the identification information of the digital assistants included in the preset interface area reaching a preset capacity, removing the identification information of at least one digital assistant that has been presented from the preset interface area; and adding the identification information of the selected candidate digital assistant to the preset interface area.

[0096] In some embodiments, the target session includes an input box, and receiving a user selection of one or more target digital assistants in the target session includes: in response to detecting user input in the input box, presenting at least one matching digital assistant that matches the user input, the user input including mention information; and receiving a selection of a matching digital assistant from the at least one matching digital assistant, with the selected matching digital assistant being determined as at least a part of the one or more target digital assistants.

[0097] In some embodiments, process 700 also includes: receiving a second message sent by the user in the target conversation; and in response to one or more target digital assistants being in a selected state, presenting one or more reply messages to the second message respectively sent by one or more target digital assistants.

[0098] In some embodiments, process 700 also includes: receiving a third message sent by the user in the target session in response to deselecting one or more target digital assistants; and presenting one or more reply messages to the third message sent by a preset digital assistant in the target session.

[0099] Example devices and equipment

[0100] 8 shows a schematic structural block diagram of an apparatus 800 for conversation interaction according to certain embodiments of the present disclosure. Apparatus 800 may be implemented as or included in terminal device 110. Each module / component in apparatus 800 may be implemented by hardware, software, firmware, or any combination thereof.

[0101] As shown in the figure, the device 800 includes a selection receiving module 810, which is configured to receive a user's selection of one or more target digital assistants in a target session, the one or more target digital assistants are not members of the target session, and the members of the target session include multiple digital assistants. The device 800 also includes a message presenting module 820, which is configured to present a first message sent by the user in the target session. The device 800 also includes a reply message presenting module 830, which is configured to present one or more reply messages to the first message respectively sent by the one or more target digital assistants.

[0102] In some embodiments, the device 800 also includes an interface area presentation module, which is configured to present an interaction window of the target session in a first interface area in response to receiving a digital assistant addition operation for the target session; and present assistant information of multiple candidate digital assistants in a second interface area, and the second interface area is at least partially different from the first interface area.

[0103] In some embodiments, the second interface area includes a search portal for searching for a digital assistant from a plurality of candidate digital assistants.

[0104] In some embodiments, assistant information of multiple candidate digital assistants is presented in the second interface area according to the grouping of the multiple candidate digital assistants.

[0105] In some embodiments, the device 800 also includes a digital assistant determination module, which is configured to target one or more interactive messages in the target session, or a digital assistant selected by the user in the target session; and present assistant information of multiple candidate digital assistants for selecting one or more target digital assistants.

[0106] In some embodiments, the selection receiving module 810 is also configured to present selection controls for at least one digital assistant in the interface of the target session; and receive trigger operations for corresponding selection controls of one or more target digital assistants in the at least one digital assistant.

[0107] In some embodiments, the device 800 also includes a control presentation module configured to present corresponding selection controls of one or more target digital assistants in a predetermined style in response to a trigger operation.

[0108] In some embodiments, the message presentation module 820 is further configured to receive user input for one or more target digital assistants; and in response to a sending operation for the user input, present the user input and mention information for the one or more target digital assistants as a first message.

[0109] In some embodiments, the mention information is presented in the first message in a preset style, and the preset style is associated with the number of the one or more target digital assistants.

[0110] In some embodiments, the message presentation module 820 is also configured to present a first message respectively mentioning one or more target digital assistants in response to selection of one or more target digital assistants from at least one digital assistant, and one or more first reply messages respectively include corresponding introductory information for the one or more target digital assistants.

[0111] In some embodiments, the selection receiving module 810 is also configured to present an add entry for adding a digital assistant in the interface of the target session; present assistant information related to at least one candidate digital assistant in response to a triggering operation on the add entry; and receive a selection of a candidate digital assistant from at least one candidate digital assistant to determine the selected candidate digital assistant as at least part of one or more target digital assistants.

[0112] In some embodiments, identification information of the selected candidate digital assistant is presented in a preset interface area of ​​the target session to indicate that the selected candidate digital assistant joins the target session.

[0113] In some embodiments, the device 800 also includes an identification information adding module, which is configured to remove the identification information of at least one digital assistant that has been presented from the preset interface area in response to the identification information of the digital assistants included in the preset interface area reaching a preset capacity; and add the identification information of the selected candidate digital assistant to the preset interface area.

[0114] In some embodiments, the target session includes an input box, and the selection receiving module 810 is further configured to, in response to detecting user input in the input box, present at least one matching digital assistant that matches the user input, the user input including mention information; and receive a selection of a matching digital assistant from the at least one matching digital assistant, with the selected matching digital assistant being determined as at least a part of the one or more target digital assistants.

[0115] In some embodiments, the reply message presentation module 830 is also configured to receive a second message sent by the user in the target conversation; and in response to one or more target digital assistants being in a selected state, present one or more reply messages for the second message respectively sent by one or more target digital assistants.

[0116] In some embodiments, the reply message presentation module 830 is also configured to receive a third message sent by the user in the target session in response to deselecting one or more target digital assistants; and present one or more reply messages to the third message issued by the preset digital assistant in the target session.

[0117] FIG9 shows a block diagram of an electronic device 900 in which one or more embodiments of the present disclosure may be implemented. It should be understood that the electronic device 900 shown in FIG9 is merely exemplary and should not be construed as limiting the functionality and scope of the embodiments described herein. The electronic device 900 shown in FIG9 can be used to implement the terminal device 110 or the server 130 of FIG1 .

[0118] As shown in FIG9 , electronic device 900 is a general-purpose electronic device. Components of electronic device 900 may include, but are not limited to, one or more processors or processing units 910, memory 920, storage device 930, one or more communication units 940, one or more input devices 950, and one or more output devices 960. Processing unit 910 may be a real or virtual processor and is capable of performing various processes according to programs stored in memory 920. In a multi-processor system, multiple processing units execute computer-executable instructions in parallel to enhance the parallel processing capabilities of electronic device 900.

[0119] The electronic device 900 typically includes a plurality of computer storage media. Such media can be any accessible media that the electronic device 900 can access, including but not limited to volatile and non-volatile media, removable and non-removable media. The memory 920 can be a volatile memory (e.g., registers, cache, random access memory (RAM)), a non-volatile memory (e.g., read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory), or some combination thereof. The storage device 930 can be a removable or non-removable medium and can include a machine-readable medium, such as a flash drive, a disk, or any other medium that can be used to store information and / or data and can be accessed within the electronic device 900.

[0120] The electronic device 900 may further include additional removable / non-removable, volatile / non-volatile storage media. Although not shown in FIG. 9 , a disk drive for reading or writing from a removable, non-volatile disk (e.g., a “floppy disk”) and an optical drive for reading or writing from a removable, non-volatile optical disk may be provided. In these cases, each drive may be connected to a bus (not shown) by one or more data media interfaces. The memory 920 may include a computer program product 925 having one or more program modules configured to perform various methods or actions of various embodiments of the present disclosure.

[0121] The communication unit 940 enables communication with other electronic devices via a communication medium. Additionally, the functions of the components of the electronic device 900 can be implemented as a single computing cluster or multiple computing machines that can communicate via a communication connection. Thus, the electronic device 900 can operate in a networked environment using a logical connection with one or more other servers, a network personal computer (PC), or another network node.

[0122] The input device 950 may be one or more input devices, such as a mouse, keyboard, or trackball. The output device 960 may be one or more output devices, such as a display, a speaker, or a printer. The electronic device 900 may also communicate with one or more external devices (not shown) through the communication unit 940 as needed, such as a storage device, a display device, or the like, with one or more devices that allow a user to interact with the electronic device 900, or with any device that allows the electronic device 900 to communicate with one or more other electronic devices (e.g., a network card, a modem, etc.). Such communication may be performed via an input / output (I / O) interface (not shown).

[0123] According to an exemplary implementation of the present disclosure, a computer-readable storage medium is provided, on which computer-executable instructions are stored, wherein the computer-executable instructions are executed by a processor to implement the method described above. According to an exemplary implementation of the present disclosure, a computer program product is also provided, which is tangibly stored on a non-transitory computer-readable medium and includes computer-executable instructions, and the computer-executable instructions are executed by a processor to implement the method described above.

[0124] Various aspects of the present disclosure are described herein with reference to flowcharts and / or block diagrams of methods, apparatuses, devices, and computer program products implemented according to the present disclosure. It should be understood that each block of the flowcharts and / or block diagrams, and combinations of blocks in the flowcharts and / or block diagrams, can be implemented by computer-readable program instructions.

[0125] These computer-readable program instructions can be provided to a processing unit of a general-purpose computer, a special-purpose computer, or other programmable data processing device, thereby producing a machine, such that when these instructions are executed by the processing unit of the computer or other programmable data processing device, a device is generated that implements the functions / actions specified in one or more blocks in the flowchart and / or block diagram. These computer-readable program instructions can also be stored in a computer-readable storage medium, where these instructions cause the computer, programmable data processing device, and / or other device to operate in a specific manner. Thus, the computer-readable medium storing the instructions comprises an article of manufacture that includes instructions for implementing various aspects of the functions / actions specified in one or more blocks in the flowchart and / or block diagram.

[0126] Computer-readable program instructions can be loaded onto a computer, other programmable data processing apparatus, or other device so that a series of operational steps are performed on the computer, other programmable data processing apparatus, or other device to produce a computer-implemented process, thereby causing the instructions executed on the computer, other programmable data processing apparatus, or other device to implement the functions / actions specified in one or more boxes in the flowchart and / or block diagram.

[0127] The flow charts and block diagrams in the accompanying drawings show the possible architecture, functions and operations of the systems, methods and computer program products according to multiple implementations of the present disclosure. In this regard, each box in the flow chart or block diagram can represent a part for a module, program segment or instruction, and a part for a module, program segment or instruction comprises one or more executable instructions for realizing the logical function of the specification. In some alternative implementations, the functions marked in the box can also occur in a sequence different from that marked in the accompanying drawings. For example, two continuous boxes can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flow chart, and the combination of the boxes in the block diagram and / or flow chart can be realized by a special hardware-based system that performs the function or action of the specification, or can be realized by a combination of special hardware and computer instructions.

[0128] While various implementations of the present disclosure have been described above, the foregoing description is intended to be illustrative, not exhaustive, and not limited to the disclosed implementations. Many modifications and variations will be apparent to those skilled in the art without departing from the scope and spirit of the described implementations. The terminology used herein is selected to best explain the principles of the implementations, their practical applications, or improvements to existing technologies, or to enable others skilled in the art to understand the various implementations disclosed herein.

Claims

1. A session interaction method, comprising: Receiving a selection of one or more target digital assistants by a user in a target session, where the one or more target digital assistants are not members of the target session, and the members of the target session include multiple digital assistants; Presenting a first message sent by the user in the target session; And Presenting one or more reply messages sent by the one or more target digital assistants respectively in response to the first message.

2. The method according to claim 1, further comprising: In response to receiving a digital assistant addition operation for the target session, Presenting an interaction window of the target session in a first interface area; And Presenting assistant information of multiple candidate digital assistants in a second interface area, where the second interface area is at least partially different from the first interface area.

3. The method according to claim 2, where the second interface area includes a search entry for searching for digital assistants from the multiple candidate digital assistants.

4. The method according to claim 2, where the assistant information of the multiple candidate digital assistants is presented in the second interface area according to the grouping of the multiple candidate digital assistants.

5. The method according to claim 1, further comprising: Determining multiple candidate digital assistants based on at least one of the following: One or more interaction messages in the target session, or The digital assistants selected by the user in the target session; And Presenting the assistant information of the multiple candidate digital assistants for selecting the one or more target digital assistants.

6. The method according to claim 1, where receiving a selection of one or more target digital assistants by a user in a target session includes: Presenting a selection control for at least one digital assistant in the interface of the target session; And Receiving a triggering operation on the corresponding selection control of the one or more target digital assistants among the at least one digital assistant.

7. The method according to claim 6, further comprising: In response to the triggering operation, presenting the corresponding selection control of the one or more target digital assistants in a predetermined style.

8. The method according to claim 6, where presenting the first message sent by the user in the target session includes: Receiving user input for the one or more target digital assistants; And In response to a sending operation for the user input, presenting the user input and mention information of the one or more target digital assistants as the first message.

9. The method according to claim 8, where the mention information is presented in the first message in a preset style, and the preset style is associated with the number of the one or more target digital assistants.

10. The method according to claim 6, where presenting the first message sent by the user in the target session includes: In response to a selection of one or more target digital assistants among the at least one digital assistant, presenting the first message respectively mentioning the one or more target digital assistants, and Each of the one or more first reply messages includes corresponding introduction information for the one or more target digital assistants.

11. The method according to claim 1, wherein receiving the user's selection of one or more target digital assistants in the target session includes: Presenting an entry for adding a digital assistant in the interface of the target session; In response to a trigger operation on the entry for adding, presenting assistant information related to at least one candidate digital assistant; And Receiving the selection of a candidate digital assistant from the at least one candidate digital assistant to determine the selected candidate digital assistant as at least part of the one or more target digital assistants.

12. The method according to claim 11, wherein the identification information of the selected candidate digital assistant is presented in a preset interface area of the target session to indicate that the selected candidate digital assistant joins the target session.

13. The method according to claim 11, further comprising: In response to the identification information of the digital assistants included in the preset interface area reaching a preset capacity, removing the identification information of at least one presented digital assistant from the preset interface area; And Adding the identification information of the selected candidate digital assistant to the preset interface area.

14. The method according to claim 1, wherein the target session includes an input box, and receiving the user's selection of one or more target digital assistants in the target session includes: In response to detecting user input in the input box, presenting at least one matching digital assistant that matches the user input, the user input including a mention; And Receiving the selection of a matching digital assistant from the at least one matching digital assistant to determine the selected matching digital assistant as at least part of the one or more target digital assistants.

15. The method according to claim 1, further comprising: Receiving a second message sent by the user in the target session; And In response to the one or more target digital assistants being in a selected state, presenting one or more reply messages sent by the one or more target digital assistants in response to the second message.

16. The method according to claim 1, further comprising: In response to canceling the selection of the one or more target digital assistants, receiving a third message sent by the user in the target session; And Presenting one or more reply messages sent by a preset digital assistant in the target session in response to the third message.

17. An apparatus for session interaction, comprising: A selection receiving module configured to receive the user's selection of one or more target digital assistants in a target session, the one or more target digital assistants not being members of the target session, and the members of the target session including a plurality of digital assistants; A message presentation module configured to present a first message sent by the user in the target session; And A reply message presentation module configured to present one or more reply messages sent by the one or more target digital assistants in response to the first message.

18. An electronic device, comprising: At least one processing unit; and at least one memory coupled to the at least one processing unit and storing instructions for execution by the at least one processing unit, the instructions when executed by the at least one processing unit causing the electronic device to perform the method according to any one of claims 1 to 16.

19. A computer-readable storage medium having stored thereon a computer program, the computer program being executable by a processor to implement the method according to any one of claims 1 to 16.

Citation Information

Patent Citations

  • Control adding method and device, equipment and storage medium

    CN113190307A

  • Session interaction method and device in robot group, equipment and storage medium

    CN113239172A

  • Interaction method and device, equipment and storage medium

    CN117376292A

  • Searching method and device, equipment and storage medium

    CN118296228A

  • Federated intelligent assistance

    US20190213490A1